AIセキュリティポータル K Program

Negative impact “Identification of training data”

This page provides the attacks and factors that have a negative impact “Identification of training data” in the information systems aspect in the AI Security Map, the defense methods and countermeasures against them, as well as the relevant AI technologies, tasks, and data. It also indicates related elements in the external influence aspect.

Attack or cause

  • Membership inference

Defensive method or countermeasure

Targeted AI technology

  • DNN
  • CNN
  • GNN
  • GAN
  • Diffusion model
  • Federated learning
  • LLM

Task

  • Classification
  • Generation

Data

  • Image
  • Graph
  • Text
  • Audio

Related external influence aspect

References